Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:226eac9da1d16dfae98e9742092d3db5948d02bcd6fdf015f9f6259d978c6328
+oid sha256:56d45a39849f9201859f4a53714dab79fc07ddbc7cb91d473f04d2cf07fbdcde
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c99c313c8ca88ec9e080f7d3ed1d80f489d4c73366c1ba8dfa6f2f610e154
+oid sha256:22c59d3ffe23d2bf61f637f3b9661fda7c87961d3b1f7c782aba5f444d9704ec
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:208b65f2b4ae56cb8de73a85ca91a54774b9f0b3186f1fa88165117387fd53e3
+oid sha256:21058290b200caf979635695ca85070470640799fa7d0341ca6289f38b1cb4cb
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.895570158958435,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 2.1306818181818183,
+  "best_metric": 1.885960340499878,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 2.2727272727272725,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 19.953,
       "eval_steps_per_second": 2.501,
       "step": 1500
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 2.0009,
+      "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 1.885960340499878,
+      "eval_runtime": 75.0366,
+      "eval_samples_per_second": 19.884,
+      "eval_steps_per_second": 2.492,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.570396780271616e+16,
+  "total_flos": 4.877824836261888e+16,
   "trial_name": null,
   "trial_params": null
 }